← Back to all news
arXiv Computer Vision By Xi Leng, Xinhong Ma, Ziqiang Dong, Feng Zhang, Xiaoying Tang, Yang Yang, Guanjun Jiang

RAVE: Re-Allocating Visual Attention in Large Multimodal Models

Read the original on arXiv Computer Vision →

RAVE (Re-Allocating Visual Attention) is a lightweight pair‑gating mechanism that adds a learned query‑key bias to pre‑softmax attention scores over visual keys, derived from pre‑RoPE query and key features. It requires no architectural changes to the backbone and can be trained end‑to‑end with the rest of the model. Across multiple multimodal benchmarks, RAVE improves standard attention by an average of 3 points, especially on perception‑intensive tasks such as multilingual OCR, chart understanding, document VQA, and scene text VQA.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Computer Vision.

Related stories

arXiv Computer Vision
Oct 5

Gaze Attention: Query-Adaptive Visual Routing for Efficient Multimodal LLMs

Gaze Attention is a new mechanism for multimodal large language models that selectively focuses on relevant visual regions during each generation step, rather than attending to all visual tokens. By grouping tokens into spatial regions and using learnable context tokens to retain global information, it reduces attention computation and visual key‑value entries by up to 90%. Experiments on 13 image and 6 video benchmarks show that Gaze Attention matches or outperforms dense‑attention baselines while using fewer visual resources.

By Junha Song, Byeongho Heo, Geonmo Gu, Jaegul Choo, Dongyoon Han, Sangdoo Yun
llmsmultimodalbenchmarks
More like this →
arXiv Computer Vision
Sep 24

VIVAS: Vitalizing Visual Perception in VLM Pre-training via Vision-language Unified Autoregressive Supervision

VIVAS is a new Vision‑Language Model pre‑training framework that addresses the lack of fine‑grained visual perception in existing VLMs. It introduces a unified token space and a dense‑structural‑semantic vision tokenizer that expands the textual vocabulary with visual tokens, enabling vision‑language unified autoregressive supervision over both visual details and linguistic content. Trained on 12.4 T tokens, VIVAS achieves state‑of‑the‑art results on 7 tasks and 39 multimodal benchmarks.

By Zhehan Kan, Yubo Zhu, Xinghua Jiang, Zhixiang Wei, Shifeng Liu, Wei Tong, Sheng Zhong, Qingmin Liao, Wenming Yang, Xin Li, Yinsong Liu, Deqiang Jiang, Xing Sun
llmsnlpmultimodalbenchmarks
More like this →
arXiv Computation and Language
Aug 31

Semantic Head Specialization Guides Hybrid ViT Attention for Multimodal LLMs

The paper introduces Semantic Head Specialization (SHS), a phenomenon where Vision Transformer (ViT) attention heads specialize as either object- or background-focused, most evident under full attention. It proposes the SHS-Index to quantify this specialization, demonstrating its ability to distinguish full-attention from chunk-window ViTs and its strong correlation with downstream benchmark performance. Leveraging insights into window interaction, token serialization, and local softmax allocation, the authors design Ariadne Attention, a hybrid attention mechanism that matches full-attention performance on 22 image and video tasks while reducing attention compute by 6.5×.

By Chenhong He, Lei Li, Shicheng Li, Hanglong Lv, Lingpeng Kong, Qi Liu, Tong Yang, Shuhuai Ren
llmsmultimodalbenchmarks
More like this →